{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2ZJ274OA5VTY6ZRAUDZGCCBBRR","short_pith_number":"pith:2ZJ274OA","canonical_record":{"source":{"id":"2007.00339","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T09:06:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee98f525b029750471aec109a3b6777b4533c714b1378369ddf45351bf09ffd2","abstract_canon_sha256":"bfe4709989000310c56b7b8aa6c38b56440df97b79836af0f1bbcc47363f589e"},"schema_version":"1.0"},"canonical_sha256":"d653aff1c0ed678f6620a0f26108218c64d88564b1313457b97d027bf27a00c7","source":{"kind":"arxiv","id":"2007.00339","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00339","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00339v4","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00339","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"2ZJ274OA5VTY","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"2ZJ274OA5VTY6ZRA","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"2ZJ274OA","created_at":"2026-07-05T02:18:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2ZJ274OA5VTY6ZRAUDZGCCBBRR","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00339","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T09:06:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee98f525b029750471aec109a3b6777b4533c714b1378369ddf45351bf09ffd2","abstract_canon_sha256":"bfe4709989000310c56b7b8aa6c38b56440df97b79836af0f1bbcc47363f589e"},"schema_version":"1.0"},"canonical_sha256":"d653aff1c0ed678f6620a0f26108218c64d88564b1313457b97d027bf27a00c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:53.387893Z","signature_b64":"KzVMWUbmXQ1wpO51tANxPVAWPt56qs/6UQKJzH7w9Xw+md6ZqNK6CyxvqmHh8WPbclei30R58R/iVdBT8udnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d653aff1c0ed678f6620a0f26108218c64d88564b1313457b97d027bf27a00c7","last_reissued_at":"2026-07-05T02:18:53.387390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:53.387390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00339","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GR/dO538CLYvmBqS++eVs8fhE1KADr6AVfmhx17GO9g99RfsiztbuVgTQMAhHXpmyp1MTYvEgOaSDatn4VQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:26:35.475123Z"},"content_sha256":"7dc421af76cdbd388146f895e876c9d92edad1dc2084f82c663d625fdbc1470d","schema_version":"1.0","event_id":"sha256:7dc421af76cdbd388146f895e876c9d92edad1dc2084f82c663d625fdbc1470d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2ZJ274OA5VTY6ZRAUDZGCCBBRR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Variational Information Bottleneck","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bowei Chen, Franck Gechter, Guanghui Wen, Weizhu Qian, Yichao Zhang","submitted_at":"2020-07-01T09:06:20Z","abstract_excerpt":"Multi-task learning (MTL) is an important subject in machine learning and artificial intelligence. Its applications to computer vision, signal processing, and speech recognition are ubiquitous. Although this subject has attracted considerable attention recently, the performance and robustness of the existing models to different tasks have not been well balanced. This article proposes an MTL model based on the architecture of the variational information bottleneck (VIB), which can provide a more effective latent representation of the input features for the downstream tasks. Extensive observatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00339","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.00339/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k524FcbgwxHqTabrL1wyf2UYNXB5sDXSR/bhnk4OhuWLkU2xnJIWEbOhydu//inBIcU1Km6Mwz6x+42gcCKbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:26:35.475936Z"},"content_sha256":"c0788d11dc560f453d24dc10dffd0d9cc92b979252730a9336cd65f8ec391b0e","schema_version":"1.0","event_id":"sha256:c0788d11dc560f453d24dc10dffd0d9cc92b979252730a9336cd65f8ec391b0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/bundle.json","state_url":"https://pith.science/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T06:26:35Z","links":{"resolver":"https://pith.science/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR","bundle":"https://pith.science/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/bundle.json","state":"https://pith.science/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZJ274OA5VTY6ZRAUDZGCCBBRR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2ZJ274OA5VTY6ZRAUDZGCCBBRR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bfe4709989000310c56b7b8aa6c38b56440df97b79836af0f1bbcc47363f589e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T09:06:20Z","title_canon_sha256":"ee98f525b029750471aec109a3b6777b4533c714b1378369ddf45351bf09ffd2"},"schema_version":"1.0","source":{"id":"2007.00339","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00339","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00339v4","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00339","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"2ZJ274OA5VTY","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"2ZJ274OA5VTY6ZRA","created_at":"2026-07-05T02:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"2ZJ274OA","created_at":"2026-07-05T02:18:53Z"}],"graph_snapshots":[{"event_id":"sha256:c0788d11dc560f453d24dc10dffd0d9cc92b979252730a9336cd65f8ec391b0e","target":"graph","created_at":"2026-07-05T02:18:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.00339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) is an important subject in machine learning and artificial intelligence. Its applications to computer vision, signal processing, and speech recognition are ubiquitous. Although this subject has attracted considerable attention recently, the performance and robustness of the existing models to different tasks have not been well balanced. This article proposes an MTL model based on the architecture of the variational information bottleneck (VIB), which can provide a more effective latent representation of the input features for the downstream tasks. Extensive observatio","authors_text":"Bowei Chen, Franck Gechter, Guanghui Wen, Weizhu Qian, Yichao Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T09:06:20Z","title":"Multi-Task Variational Information Bottleneck"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00339","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7dc421af76cdbd388146f895e876c9d92edad1dc2084f82c663d625fdbc1470d","target":"record","created_at":"2026-07-05T02:18:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bfe4709989000310c56b7b8aa6c38b56440df97b79836af0f1bbcc47363f589e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T09:06:20Z","title_canon_sha256":"ee98f525b029750471aec109a3b6777b4533c714b1378369ddf45351bf09ffd2"},"schema_version":"1.0","source":{"id":"2007.00339","kind":"arxiv","version":4}},"canonical_sha256":"d653aff1c0ed678f6620a0f26108218c64d88564b1313457b97d027bf27a00c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d653aff1c0ed678f6620a0f26108218c64d88564b1313457b97d027bf27a00c7","first_computed_at":"2026-07-05T02:18:53.387390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:18:53.387390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KzVMWUbmXQ1wpO51tANxPVAWPt56qs/6UQKJzH7w9Xw+md6ZqNK6CyxvqmHh8WPbclei30R58R/iVdBT8udnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:18:53.387893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00339","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc421af76cdbd388146f895e876c9d92edad1dc2084f82c663d625fdbc1470d","sha256:c0788d11dc560f453d24dc10dffd0d9cc92b979252730a9336cd65f8ec391b0e"],"state_sha256":"128e5720232367ed52a25f2591d810e96cae45fb6a7e73df2de1a0dc6ecc3c08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3RP8BNcqQebXVo6l//VncvW7QIYXkD6YmdyQ/vtyV4dNehCXW+K04IBOutPjC+VUPVeE8LMd3dAt4118aCpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:26:35.482296Z","bundle_sha256":"9e5908c5e1b84e24a09e70a63499ae3d791e1338327b9eea9d0800a0dcb7ee91"}}